Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
6 min · · экономия
We price requests to GPT models at October 18, 2026 rates: the formula, the role of cache, three scenarios and a comparison with official tariffs.
5 min · · development
A model can draft a sketch but cannot see your wiring. How to describe the board, check code before uploading and debug using Serial output.
6 min · · экономия
We price GLM 5.3 and GLM 5.3 Flash on three scenarios and explain why a single input and output price helps with long answers.
5 min · · сравнение
Astra and Sol from the GPT-6 family differ in price and Intelligence Index. We price the same task on both and give a simple selection rule.
5 min · · errors
Access errors for ChatGPT and the OpenAI API explained, with their causes and a way to use GPT models through a gateway in chat and via the API.
5 min · · API keys
The Claude API gives your code access to the models and is billed per token. The Messages API, caching and tools explained, with a first request.
5 min · · агенты
An agent is a model that picks its own actions and repeats a loop until the task is done. The structure, examples and honest limits.
5 min · · сравнение
Two terminal agents with a similar feature set. We compare setup, models and API cost so the choice is not a blind one.
5 min · · development
A model cannot see your configuration and may invent methods and attributes. Here is how to give them metadata and examples, verify the code and estimate request costs.
5 min · · models
Three working ways to use Claude Opus 5.5 from Russia: web chat, an API request and Claude Code. With code and a cost estimate at October 18, 2026 prices.
5 min · · development
Made-up facts cannot be removed completely, but they can be made rare and visible. The causes and five measures with working Python code.
5 min · · development
A good prompt is not a spell but six concrete parts. We show them on one example where both the answer and the request price change.
5 min · · API keys
A permanently free key does not exist: the API is paid per token. Why keys found online are dangerous, and how many requests a one-dollar balance buys.
5 min · · автоматизация
Good English depends on parameters people often forget to set: audience, register, language variant. A prompt, back-translation checks and the price of a batch.
6 min · · сравнение
Both live in the terminal and connect to third-party models, but they are built differently: aider drives git for you, opencode is closer to an agent workbench.
6 min · · IDE
What GitHub Copilot is, what it consists of and how it differs from Cline, Cursor and Claude Code, and when you need your own key.
4 min · · автоматизация
Natural Russian comes from an instruction, a glossary and automated checks, not from picking a single "best" model. A scheme with code and a price comparison.
6 min · · IDE
What makes GitHub Copilot a question mark for users in Russia, and which alternatives work in VS Code on your own API key.
5 min · · development
You do not need an editor to get started: a browser and a key are enough. Working prompts, model choice and the price of a typical conversation.
5 min · · API keys
There is no permanent free Anthropic key, and trial terms change. How a key is created, where the catch is, and what a Claude test costs.
6 min · · models
Ollama runs open language models on your computer and serves them over a local API. What it can and can't do, and when a cloud API is the better fit.
4 min · · API keys
An API lets your code call a model instead of a person typing in a chat. A look at requests, responses and why the OpenAI format is used far beyond the company itself.
5 min · · models
The context window is a model's entire working memory for one request: prompt, history, files and the answer. How to count it and what a long context costs.
5 min · · development
A step-by-step business-card site built with the Claude Code agent, with a cost estimate, and an honest note on where "free" ends.